Metrics
6 Record Views
Journal article
REDS: Random ensemble deep spatial prediction
Environmetrics (London, Ont.), Vol.34(1), e2780
02/2023
Web of Science ID: WOS:001136632300012
Abstract
There has been a great deal of recent interest in the development of spatial prediction algorithms for very large datasets and/or prediction domains. These methods have primarily been developed in the spatial statistics community, but there has been growing interest in the machine learning community for such methods, primarily driven by the success of deep Gaussian process regression approaches and deep convolutional neural networks. These methods are often computationally expensive to train and implement and consequently, there has been a resurgence of interest in random projections and deep learning models based on random weights-so called reservoir computing methods. Here, we combine several of these ideas to develop the random ensemble deep spatial (REDS) approach to predict spatial data. The procedure uses random Fourier features as inputs to an extreme learning machine (a deep neural model with random weights), and with calibrated ensembles of outputs from this model based on different random weights, it provides a simple uncertainty quantification. The REDS method is demonstrated on simulated data and on a classic large satellite data set.
Related links
Details
- Title
- REDS: Random ensemble deep spatial prediction
- Publication Details
- Environmetrics (London, Ont.), Vol.34(1), e2780
- Resource Type
- Journal article
- Publisher
- Wiley
- Number of pages
- 15
- Grant note
- SES-1853096; CNS-1429294 / U.S. National Science Foundation; National Science Foundation (NSF)
- Copyright
- © 2022 John Wiley & Sons Ltd.
- Identifiers
- WOS:001136632300012; 99381289139506600
- Academic Unit
- Hal Marcus College of Science and Engineering ; Mathematics and Statistics
- Language
- English